# \#relations **URL:** https://support.prodi.gy/tag/relations/58.md [Latest](https://support.prodi.gy/latest.md) · [Categories](https://support.prodi.gy/categories.md) · [Tags](https://support.prodi.gy/tags.md) --- ## [Guidance Needed on Using LLMs with Prodigy for Spanish Coreference Annotation](https://support.prodi.gy/t/guidance-needed-on-using-llms-with-prodigy-for-spanish-coreference-annotation/7666)
**Author:** [@angelo](https://support.prodi.gy/u/angelo)\ **Replies:** 1\ **Last updated:** [May 14, 2026, 2:40pm UTC](https://support.prodi.gy/t/guidance-needed-on-using-llms-with-prodigy-for-spanish-coreference-annotation/7666 "2026-05-14T14:40:30Z")
Hello, I hope you are doing well. I am currently trying to train a spaCy model to resolve coreferences with good accuracy in Spanish. My main challenge is that I need to annotate thousands of text entries, and I am no… --- ## [Is it possible to have a recipe receive multiple streams?](https://support.prodi.gy/t/is-it-possible-to-have-a-recipe-receive-multiple-streams/7535)
**Author:** [@SanVijey](https://support.prodi.gy/u/SanVijey)\ **Replies:** 1\ **Last updated:** [April 8, 2025, 4:53pm UTC](https://support.prodi.gy/t/is-it-possible-to-have-a-recipe-receive-multiple-streams/7535 "2025-04-08T16:53:33Z")
We are currently creating a relations recipe, which consists of two blocks. We want the relations block to only consist of the numerical tokens/spans of the text (as those tokens are what we are creating relationships be… --- ## [Prodigy hangs when streaming into rel.manual](https://support.prodi.gy/t/prodigy-hangs-when-streaming-into-rel-manual/7459)
**Author:** [@FourthPartyAI](https://support.prodi.gy/u/FourthPartyAI)\ **Replies:** 5\ **Last updated:** [December 10, 2024, 11:50am UTC](https://support.prodi.gy/t/prodigy-hangs-when-streaming-into-rel-manual/7459 "2024-12-10T11:50:01Z")
I have StreamManager that loads data from a Prodigy dataset backed by Postgres. It works fine for spans, but when I switch over to relationships I get odd behavior... In both cases I have a wrapper recipe, the spans exa… --- ## [Broken link in documentation for "Example: Checking a single example against GPT-4"](https://support.prodi.gy/t/broken-link-in-documentation-for-example-checking-a-single-example-against-gpt-4/7320)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 3\ **Last updated:** [August 4, 2024, 7:34am UTC](https://support.prodi.gy/t/broken-link-in-documentation-for-example-checking-a-single-example-against-gpt-4/7320 "2024-08-04T07:34:18Z")
Hi, I want to use an LLM to pre-annotate NER and relationships between entities and then have those annotations be reviewed and refined by human annotators. However, the documentation section for "Example: Checking a si… --- ## [Inquiry on Using Relation Extraction Model for Annotation in Prodigy](https://support.prodi.gy/t/inquiry-on-using-relation-extraction-model-for-annotation-in-prodigy/7254)
**Author:** [@othmane](https://support.prodi.gy/u/othmane)\ **Replies:** 6\ **Last updated:** [June 10, 2024, 11:09am UTC](https://support.prodi.gy/t/inquiry-on-using-relation-extraction-model-for-annotation-in-prodigy/7254 "2024-06-10T11:09:45Z")
Hello , I am currently training a Named Entity Recognition and Relation Extraction model. I have been using the rel.manual recipe to annotate the relations in my documents and have followed the approach outlined in the… --- ## [Loading non-Prodigy pre-annotated text](https://support.prodi.gy/t/loading-non-prodigy-pre-annotated-text/7245)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 1\ **Last updated:** [May 28, 2024, 12:54pm UTC](https://support.prodi.gy/t/loading-non-prodigy-pre-annotated-text/7245 "2024-05-28T12:54:41Z")
Hi, I want to load into Prodigy some pre-annotated texts for Relation Extraction from an open-source study. My idea is to review the annotated data and modify NER and RE labels based on different annotation guidelines. … --- ## [Repeated sentences and incorrect annotator id](https://support.prodi.gy/t/repeated-sentences-and-incorrect-annotator-id/7229)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 1\ **Last updated:** [May 20, 2024, 11:52am UTC](https://support.prodi.gy/t/repeated-sentences-and-incorrect-annotator-id/7229 "2024-05-20T11:52:56Z")
Hi, My team is working on annotating both NER and RE with the rel.manual recipe. For this, I am using the following config (prodigy.json): { "feed\_overlap": true, "custom\_theme": { "cardMaxWidth": 1500,… --- ## [Review recipe for relationships not grouping same annotations](https://support.prodi.gy/t/review-recipe-for-relationships-not-grouping-same-annotations/7220)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 5\ **Last updated:** [May 17, 2024, 10:32pm UTC](https://support.prodi.gy/t/review-recipe-for-relationships-not-grouping-same-annotations/7220 "2024-05-17T22:32:13Z")
Hi, I am reviewing a relationships dataset created with rel.manual and annotated by 3 annotators. I noticed the recipe wouldn't group identical annotations due to the order in which the were made. For example, in the at… --- ## [Reviewing both relationships as well as entities](https://support.prodi.gy/t/reviewing-both-relationships-as-well-as-entities/7219)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 3\ **Last updated:** [May 15, 2024, 8:59am UTC](https://support.prodi.gy/t/reviewing-both-relationships-as-well-as-entities/7219 "2024-05-15T08:59:37Z")
Hi, My team annotated text for both entities and relationships using rel.manual and the options --label (for relationships) and --span-label (for entities). However, the review recipe it doesn't accept the --span-label … --- ## [How to load a Hugging Face model's annotations in Prodigy](https://support.prodi.gy/t/how-to-load-a-hugging-face-models-annotations-in-prodigy/7218)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 3\ **Last updated:** [May 13, 2024, 11:04am UTC](https://support.prodi.gy/t/how-to-load-a-hugging-face-models-annotations-in-prodigy/7218 "2024-05-13T11:04:48Z")
Hi, I have a HF model that can annotate the named entities I am interested in. I want to run rel.manual on top of those annotations to 1) correct some of the NER label annotations , and 2) annotate the relationships bet… --- ## [Customizing rel.manual interface](https://support.prodi.gy/t/customizing-rel-manual-interface/7199)
**Author:** [@ale](https://support.prodi.gy/u/ale)\ **Replies:** 3\ **Last updated:** [May 9, 2024, 10:53am UTC](https://support.prodi.gy/t/customizing-rel-manual-interface/7199 "2024-05-09T10:53:33Z")
Hi, My team will be annotating paragraphs for relation extraction of inter- and cross-sentence relationships. It seems that the approach we will take is to have text annotated for entities first, and then use rel.manual … --- ## [rel.manual not accepting entities because of tokenization](https://support.prodi.gy/t/rel-manual-not-accepting-entities-because-of-tokenization/3536)
**Author:** [@yys](https://support.prodi.gy/u/yys)\ **Replies:** 7\ **Last updated:** [April 17, 2024, 9:11am UTC](https://support.prodi.gy/t/rel-manual-not-accepting-entities-because-of-tokenization/3536 "2024-04-17T09:11:04Z")
Hi, I'm trying to relate some pre-annotated entities. However, when I feed a dataset with them to rel.manual: prodigy rel.manual test\_dataset\_rel en\_core\_web\_sm dataset:test\_dataset -l SUBJECT it throws a bunch of few… --- ## [Annotating references between bounding boxes for document understanding](https://support.prodi.gy/t/annotating-references-between-bounding-boxes-for-document-understanding/7110)
**Author:** [@HerrSebi](https://support.prodi.gy/u/HerrSebi)\ **Replies:** 1\ **Last updated:** [February 28, 2024, 5:17pm UTC](https://support.prodi.gy/t/annotating-references-between-bounding-boxes-for-document-understanding/7110 "2024-02-28T17:17:47Z")
My use case is creating a dataset to train models on data extraction from CV PDFs. The CVs are notoriously weird in their structuring, and I've been using the PDF and OCR recipes to annotate things like previous experien… --- ## [Open labeling with text boxes](https://support.prodi.gy/t/open-labeling-with-text-boxes/7099)
**Author:** [@alan-hogue](https://support.prodi.gy/u/alan-hogue)\ **Replies:** 3\ **Last updated:** [February 23, 2024, 10:30am UTC](https://support.prodi.gy/t/open-labeling-with-text-boxes/7099 "2024-02-23T10:30:44Z")
I would like to do entity linking using wikidata, but would like to allow the annotator to search wikidata and enter whichever ID they decide is the right one, rather than giving them a list to choose from. I think this… --- ## [How to do relation annotation after using bert.mer.manual](https://support.prodi.gy/t/how-to-do-relation-annotation-after-using-bert-mer-manual/6612)
**Author:** [@Jiachen](https://support.prodi.gy/u/Jiachen)\ **Replies:** 2\ **Last updated:** [December 12, 2023, 10:47pm UTC](https://support.prodi.gy/t/how-to-do-relation-annotation-after-using-bert-mer-manual/6612 "2023-12-12T22:47:59Z")
Hi, I'm using Prodigy to do annotation for fine-tuning BERTs, which aims to do the NER and RE tasks. I've annotated the NER with the 'bert.ner.manual' recipe. I wondered if there is a recipe for relation annotation using… --- ## [Wrap breaks for long documents](https://support.prodi.gy/t/wrap-breaks-for-long-documents/6891)
**Author:** [@Martin](https://support.prodi.gy/u/Martin)\ **Replies:** 3\ **Last updated:** [November 16, 2023, 9:57am UTC](https://support.prodi.gy/t/wrap-breaks-for-long-documents/6891 "2023-11-16T09:57:37Z")
Hi everyone, I have a specific need to annotate quite long documents with relations and entities, also showing some metadata, and we have begun work on a custom recipe to do that. We want to have the full document in ou… --- ## [Existing entity label data to solve the relationship annotation in different statements](https://support.prodi.gy/t/existing-entity-label-data-to-solve-the-relationship-annotation-in-different-statements/6836)
**Author:** [@luoshengmen98](https://support.prodi.gy/u/luoshengmen98)\ **Replies:** 1\ **Last updated:** [October 11, 2023, 3:36pm UTC](https://support.prodi.gy/t/existing-entity-label-data-to-solve-the-relationship-annotation-in-different-statements/6836 "2023-10-11T15:36:02Z")
Hello, I have trained and done a good job of named entity recognition; At this stage, it is necessary to label the entities in the text, but there is a problem that none of the data in the output jsonl file is short, and… --- ## [Querying Relations Layer Annotations (for Rhetoric Text Structure Analysis)](https://support.prodi.gy/t/querying-relations-layer-annotations-for-rhetoric-text-structure-analysis/6759)
**Author:** [@yanirmr](https://support.prodi.gy/u/yanirmr)\ **Replies:** 3\ **Last updated:** [September 6, 2023, 10:57am UTC](https://support.prodi.gy/t/querying-relations-layer-annotations-for-rhetoric-text-structure-analysis/6759 "2023-09-06T10:57:57Z")
Hello, I'm embarking on a project focused on tagging relationships between entities to annotate the structure of rhetorical texts. The goal is to identify and analyze structures such as claims, rhetorical questions, fac… --- ## [Inquiries about Prodigy 1.12 and Future GPT-4 Integration](https://support.prodi.gy/t/inquiries-about-prodigy-1-12-and-future-gpt-4-integration/6665)
**Author:** [@naumanshah007](https://support.prodi.gy/u/naumanshah007)\ **Replies:** 1\ **Last updated:** [July 10, 2023, 10:02am UTC](https://support.prodi.gy/t/inquiries-about-prodigy-1-12-and-future-gpt-4-integration/6665 "2023-07-10T10:02:02Z")
Hello Prodigy Support Team, I hope this message finds you well. I have recently upgraded to Prodigy 1.12 and have been enjoying the new features and enhancements. I had a couple of questions that I was hoping you could … --- ## [Allowing implicit words in relation extraction](https://support.prodi.gy/t/allowing-implicit-words-in-relation-extraction/6639)
**Author:** [@KennethEnevoldsen](https://support.prodi.gy/u/KennethEnevoldsen)\ **Replies:** 2\ **Last updated:** [June 30, 2023, 9:43pm UTC](https://support.prodi.gy/t/allowing-implicit-words-in-relation-extraction/6639 "2023-06-30T21:43:09Z")
We have a project where we are working on annotating relations for open-relation extraction. Imagine a sentence like this: "This forum the official place to discuss Prodigy" You would like to annotate it: Triplet: … --- ## [Training a relation extraction component](https://support.prodi.gy/t/training-a-relation-extraction-component/6376)
**Author:** [@stella](https://support.prodi.gy/u/stella)\ **Replies:** 84\ **Last updated:** [June 27, 2023, 12:36pm UTC](https://support.prodi.gy/t/training-a-relation-extraction-component/6376 "2023-06-27T12:36:24Z")
Hi, I'm using the rel.manual recipe to annotate named entities as well as relations in a training dataset. Both tasks are done at the same time, --label enabling to annotate relations while --span-label enables named e… --- ## [Is Prodigy suitable for cross-document coreference resolution with diverse types of entities and reference?](https://support.prodi.gy/t/is-prodigy-suitable-for-cross-document-coreference-resolution-with-diverse-types-of-entities-and-reference/6563)
**Author:** [@jakob.vogel](https://support.prodi.gy/u/jakob.vogel)\ **Replies:** 2\ **Last updated:** [June 7, 2023, 8:41am UTC](https://support.prodi.gy/t/is-prodigy-suitable-for-cross-document-coreference-resolution-with-diverse-types-of-entities-and-reference/6563 "2023-06-07T08:41:42Z")
I am looking for a tool where I can annotate coreferences across documents. Additionally, the tool should allow for defining several types of (co)reference. Furthermore, it should be possible to define several types of e… --- ## [Rel training](https://support.prodi.gy/t/rel-training/5331)
**Author:** [@pkras](https://support.prodi.gy/u/pkras)\ **Replies:** 7\ **Last updated:** [May 22, 2023, 1:14pm UTC](https://support.prodi.gy/t/rel-training/5331 "2023-05-22T13:14:03Z")
Hello! This is somewhat of a follow up to my previous posts, but made a separate topic for clarity. I have seen similar topics, but still it is not really clear to me what i should do. I have annotated and trained a N… --- ## [Dependency parsing with multiple keywords](https://support.prodi.gy/t/dependency-parsing-with-multiple-keywords/6488)
**Author:** [@AmirNickkar](https://support.prodi.gy/u/AmirNickkar)\ **Replies:** 2\ **Last updated:** [April 11, 2023, 7:50pm UTC](https://support.prodi.gy/t/dependency-parsing-with-multiple-keywords/6488 "2023-04-11T19:50:11Z")
I want to find the possible relationships between three group of keywords in a text. These groups are ingredient \_keywords, food\_keywords, and adverse\_event\_keywords. Let's say that the text is "Too much salt in cheese m… --- ## [Linking Labels](https://support.prodi.gy/t/linking-labels/6386)
**Author:** [@Mohammad](https://support.prodi.gy/u/Mohammad)\ **Replies:** 1\ **Last updated:** [February 24, 2023, 6:31pm UTC](https://support.prodi.gy/t/linking-labels/6386 "2023-02-24T18:31:40Z")
Hello, After I trained the model to extract "CompaniesWorkedAt" ,"Designation" and "Location" the model predict labels that not linking to each other . How I can add relation between the entities or link entities to tog… --- ## [prodigy data-to-spacy for relation extraction](https://support.prodi.gy/t/prodigy-data-to-spacy-for-relation-extraction/5620)
**Author:** [@nemomar](https://support.prodi.gy/u/nemomar)\ **Replies:** 4\ **Last updated:** [February 23, 2023, 9:07pm UTC](https://support.prodi.gy/t/prodigy-data-to-spacy-for-relation-extraction/5620 "2023-02-23T21:07:34Z")
First of all thanks for the excellent tool. I want to convert my .jsonl file that contains annotated data to .spacy binary files for training a relation extraction (RE) model. I succeed to do it for the NER part with: … --- ## [NER and relation\_extractor with transformer.](https://support.prodi.gy/t/ner-and-relation-extractor-with-transformer/6369)
**Author:** [@abhishekshingadiya](https://support.prodi.gy/u/abhishekshingadiya)\ **Replies:** 1\ **Last updated:** [February 15, 2023, 7:37pm UTC](https://support.prodi.gy/t/ner-and-relation-extractor-with-transformer/6369 "2023-02-15T19:37:05Z")
Hello there, I am trying to make NER (18 Entities ) and relation\_extractor (7 relations) both together. Every document has an average of 3k tokens per document. sentence segmentation is not possible because the text is… --- ## [Training BERT on prodigy](https://support.prodi.gy/t/training-bert-on-prodigy/6339)
**Author:** [@Mohammad](https://support.prodi.gy/u/Mohammad)\ **Replies:** 3\ **Last updated:** [February 2, 2023, 3:09pm UTC](https://support.prodi.gy/t/training-bert-on-prodigy/6339 "2023-02-02T15:09:24Z")
After I did the annotation on prodigy how I can run training on prodigy for BERT python3 -m prodigy bert.ner.manual correctd\_drsv1 ./model\_drsv1 ./CV\_json\_English\_Format.jsonl --label Skill,MaritalStatus,University,De… --- ## [Prodigy relations](https://support.prodi.gy/t/prodigy-relations/6307)
**Author:** [@Mohammad](https://support.prodi.gy/u/Mohammad)\ **Replies:** 1\ **Last updated:** [January 31, 2023, 12:28pm UTC](https://support.prodi.gy/t/prodigy-relations/6307 "2023-01-31T12:28:05Z")
What is prodigy relations" command can be used to train a relation extraction model which is a NLP task that aims to identify relationships between entities in a text. --- ## [right to left UI](https://support.prodi.gy/t/right-to-left-ui/5138)
**Author:** [@aisha\_harbi](https://support.prodi.gy/u/aisha_harbi)\ **Replies:** 2\ **Last updated:** [January 25, 2023, 2:27pm UTC](https://support.prodi.gy/t/right-to-left-ui/5138 "2023-01-25T14:27:54Z")
I have downloaded prodigy on the same machine before and tried modifying the writing\_dir = rtl and it worked great. I'm currently running this old NER recipe and the text is rtl which is what I want, but I am working wit… [Next page](https://support.prodi.gy/tag/relations/58.md?match_all_tags=true&page=1&tags%5B%5D=relations)